Skip to content
/ UserAIF Public

Addressing Selection Bias in Computerized Adaptive Testing: A User-Wise Aggregate Influence Function Approach (CIKM'23)

License

Notifications You must be signed in to change notification settings

riiid/UserAIF

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Addressing Selection Bias in Computerized Adaptive Testing: A User-Wise Aggregate Influence Function Approach

Official Pytorch implementation of the paper "Addressing Selection Bias in Computerized Adaptive Testing: A User-Wise Aggregate Influence Function Approach"

Requirements

pip install -r requirements.txt

Training

1) unbiasead + biased

python main_train.py

2) unbiased

python main_train.py data.path_dict.biased_users=""

3) unbiasead + selected biased (UserAIF)

python main_train.py user_aif=True

About

Addressing Selection Bias in Computerized Adaptive Testing: A User-Wise Aggregate Influence Function Approach (CIKM'23)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages